© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40304
    Prev
    Next
    INDEX
    Explanations

    simple, short, direct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æį®è¯´
    -0.07
    ä¼łè¯´ä¸Ń
    -0.07
    æŀģ好
    -0.07
    æŀģ好çļĦ
    -0.07
    æŀģ
    -0.07
    åıĸéķ¿è¡¥çŁŃ
    -0.07
    artal
    -0.07
     purported
    -0.07
    åĦ¿æŶ
    -0.06
    ARGE
    -0.06
    POSITIVE LOGITS
    ä½Ĩä»į
    0.08
    ä½Ĩåı¯ä»¥
    0.08
    ä½Ĩä»įçĦ¶
    0.08
    ä½Ĩèĩ³å°ij
    0.08
    ä½Ĩä¹Ł
    0.08
    ä½Ĩåľ¨
    0.08
     but
    0.08
    ellini
    0.07
     gá»įn
    0.07
    оÑĤÑĢе
    0.07
    Activations Density 0.001%

    No Known Activations